An intelligent rehabilitation and nursing management system based on data analysis

Abstract

This invention relates to the field of data processing technology, specifically to an intelligent rehabilitation and nursing management system based on data analysis. The system includes: a motion state acquisition module that acquires raw electromyographic signals and joint torque and angle values; a physiological characteristic analysis module that extracts the median frequency sequence in the frequency domain and constructs an electromyographic fatigue gradient; a motion compensation calculation module that calculates the end-effector driving torque and generates a motion compensation coefficient; and an adaptive control execution module that calculates the resistance increment based on the fatigue gradient and calculates virtual wall parameters to construct a control strategy when the compensation coefficient exceeds the limit. In this invention, by combining frequency domain analysis to construct a fatigue gradient, using a dynamic model to calculate the compensation ratio, adjusting resistance based on the compensation coefficient and fatigue state, and constructing virtual wall constraints, quantitative analysis of physiological characteristics and motion states is achieved. This ensures adaptive matching of the optimal strategy while guaranteeing safety, thereby improving the intelligence and accuracy of training.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an intelligent rehabilitation and nursing management system based on data analysis. Background Technology

[0002] Data processing technology refers to the technical field of collecting, storing, retrieving, converting, and processing various types of digital information using computer hardware and software systems. Traditional intelligent rehabilitation and nursing management systems refer to local area network (LAN) information entry platforms built on a client / server (C / S) architecture. Their physical components typically include desktop computers for medical and nursing staff, barcode scanners, network switches, and a central database server. Medical staff use a physical keyboard and mouse to input patients' basic identity information, daily vital signs data, and rehabilitation training items into fixed forms on the workstation software. The data is transmitted via network lines and stored in structured tables on the server's hard drive. The system performs simple archiving and retrieval of individual data fields according to preset logical rules.

[0003] Existing systems heavily rely on manual, mechanical data entry via physical peripherals, resulting in cumbersome, inefficient, and easily subject to human error. Their fixed form-based storage mode only allows for simple archiving of static results, failing to perceive dynamic physiological changes and subtle movements during patient training in real time. This offline management makes it difficult for the system to capture muscle fatigue and compensatory movement trends, causing training plans to become disconnected from the patient's actual function, reducing the relevance and effectiveness of treatment, and making it impossible to intervene in time when the patient's movements become distorted, thus creating a risk of secondary injury. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing an intelligent rehabilitation and nursing management system based on data analysis.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent rehabilitation and nursing management system based on data analysis includes:

[0006] The motion state acquisition module activates multi-channel sensors to acquire raw electromyographic voltage signals of the target muscle group and compensatory muscle group, reads the real-time joint torque value output by the joint torque sensor of the rehabilitation robotic arm, and obtains the real-time angle value fed back by the position encoder.

[0007] The physiological feature analysis module performs a fast Fourier transform on the original electromyographic voltage signal to calculate the power spectral density distribution, extracts the median frequency point sequence in the frequency domain from the power spectral density distribution, calls a linear regression model to calculate the time evolution slope value of the median frequency point sequence in the frequency domain, and constructs the electromyographic fatigue gradient.

[0008] The motion compensation calculation module inputs the real-time joint torque value and the real-time angle value into the rigid body dynamics model to solve the end-drive torque, decomposes the end-drive torque into a target torque component and a compensation torque component, calculates the proportion of the compensation torque component in the end-drive torque, and generates a motion compensation coefficient.

[0009] The adaptive control execution module calculates the resistance increment value based on the electromyographic fatigue gradient and generates a motor current control command. When the motion compensation coefficient exceeds a preset threshold, it calculates the spatial coordinate constraint parameters of the reverse virtual wall and constructs a rehabilitation control strategy based on the motor current control command and the spatial coordinate constraint parameters.

[0010] As a further aspect of the present invention, the specific function of the motion state acquisition module is as follows:

[0011] The signal sensing submodule responds to the system start command to activate the multi-channel electromyographic electrode pads attached to the patient's skin surface, and synchronously captures the weak bioelectric signals of the target muscle group and the compensating muscle group at a preset high-frequency sampling rate. The weak bioelectric signals are pre-amplified and filtered to generate the original electromyographic voltage signal.

[0012] The kinematic reading submodule accesses the joint actuator interface of the rehabilitation robotic arm in real time via the communication bus, reads torque feedback data from multiple joint torque sensors under high dynamic motion, and simultaneously acquires absolute angle position data output by the joint position encoder. The torque feedback data and the absolute angle position data are then time-stamped and denoised to generate the real-time joint torque value and the real-time angle value.

[0013] As a further aspect of the present invention, the specific function of the physiological characteristic analysis module is as follows:

[0014] The spectrum conversion submodule applies windowing truncation processing to the original electromyographic voltage signal in the time domain, uses the fast Fourier transform algorithm to map the time domain signal to the frequency domain space, calculates the energy amplitude of multiple frequency components, and generates the power spectral density distribution that characterizes the frequency structure features of the electromyographic signal.

[0015] The frequency extraction submodule traverses the power spectral density distribution and calculates the cumulative power spectral energy, identifies the frequency boundary point that divides the cumulative power spectral energy into two equal parts, and continuously extracts the frequency boundary point according to the time sliding window to generate the frequency domain median frequency point sequence.

[0016] The fatigue assessment submodule uses the mid-frequency point sequence in the frequency domain as the dependent variable and the time series as the independent variable to establish a least squares linear regression equation. It analyzes the slope term of the least squares linear regression equation to quantify the degree of frequency center drift towards lower frequencies and generates the electromyographic fatigue gradient.

[0017] As a further aspect of the present invention, the specific function of the motion compensation calculation module is as follows:

[0018] The dynamics solution submodule obtains the link mass parameters and inertia tensor matrix of the robotic arm, and combines the real-time joint torque value and the real-time angle value to use the Lagrange dynamics equation to solve the force state of the robotic arm end effector in the Cartesian coordinate system, thereby generating the end-effector driving torque.

[0019] The torque decomposition submodule obtains the preset standard rehabilitation training trajectory tangent vector, orthogonally projects the end driving torque onto the direction of the standard rehabilitation training trajectory tangent vector to separate the target torque component, and defines the remaining vector after removing the target torque component from the end driving torque as the compensating torque component.

[0020] The coefficient generation submodule calculates the ratio between the modulus of the compensating torque component and the modulus of the end drive torque, and performs a weighted correction on the ratio in conjunction with the current motion smoothness index to generate the motion compensation coefficient.

[0021] As a further aspect of the present invention, the specific function of the adaptive control execution module is as follows:

[0022] The resistance adjustment submodule establishes a nonlinear mapping relationship between the electromyographic fatigue gradient and the motor output impedance. As the electromyographic fatigue gradient increases, the training resistance setting value is dynamically reduced. Based on the adjusted training resistance setting value, the target current values ​​of multiple joint motors are calculated, and the motor current control command is generated.

[0023] The constraint construction submodule monitors the motion compensation coefficient in real time. When the motion compensation coefficient exceeds the preset compensation range, it generates a virtual force field boundary with stiffness and damping characteristics outside the standard trajectory based on the current deviation direction, calculates the geometric position data of the virtual force field boundary, and generates the spatial coordinate constraint parameters.

[0024] The strategy fusion submodule uses the motor current control command as the underlying torque following basis and the spatial coordinate constraint parameters as position restriction conditions. The torque control and position restriction are logically superimposed through the impedance controller to generate the rehabilitation control strategy.

[0025] As a further aspect of the present invention, the specific process by which the frequency extraction submodule calculates the mid-frequency point sequence in the frequency domain includes:

[0026] Obtain the power spectral density distribution within the current analysis window, and calculate the total power energy value across the entire frequency band from the DC component to the highest effective frequency within the current analysis window;

[0027] The power spectral density distribution is integrated and accumulated starting from zero frequency, and the ratio between the accumulated energy value and the total power energy value of the entire frequency band is monitored in real time.

[0028] When the accumulated energy value first reaches 50% of the total power energy value of the entire frequency band, the corresponding frequency value is locked and the frequency value is marked as the median frequency point of the current analysis window.

[0029] As the time window slides continuously, the above calculation process is repeated, and the median frequency points obtained in sequence are arranged in chronological order to generate the frequency domain median frequency point sequence.

[0030] As a further aspect of the present invention, the process of constructing the electromyographic fatigue gradient by the fatigue assessment submodule includes:

[0031] Obtain the frequency point sequence of the frequency domain of the preset length, construct a dataset including time variables and frequency variables, and fit the trend line of the dataset using a univariate linear regression algorithm;

[0032] Extract the slope parameter of the trend line, determine the sign and magnitude of the slope parameter, and if the slope parameter is negative, define the absolute value of the slope parameter as a quantitative index of muscle fatigue after standardization.

[0033] The muscle fatigue quantification index is normalized and corrected by combining the physiological tolerance benchmarks of multiple muscle groups to generate the electromyographic fatigue gradient.

[0034] As a further aspect of the present invention, the process by which the dynamics solution submodule generates the end-drive torque includes:

[0035] Call the robot arm link length, link center of mass position and link mass parameters stored in the system database;

[0036] Based on the real-time angle values, the angular velocities and angular accelerations of multiple joints are calculated. According to the inverse kinematics algorithm, the theoretical joint torque required to counteract the gravity term, Coriolis force term, and centrifugal force term is calculated.

[0037] The difference vector between the real-time joint torque value and the theoretical joint torque is calculated, and the difference vector is mapped to the end effector space using the Jacobian matrix transpose method to generate the end effector driving torque.

[0038] As a further aspect of the present invention, the process by which the constraint construction submodule generates the spatial coordinate constraint parameters includes:

[0039] Obtain a three-dimensional spatial point set of the standard rehabilitation trajectory; when the motion compensation coefficient exceeds a preset threshold, calculate the normal deviation distance between the current actual position of the end effector and the standard rehabilitation trajectory.

[0040] A virtual elastic potential energy field is constructed based on the normal deviation distance. The repulsive force direction of the virtual elastic potential energy field is set to be perpendicular to the inside of the standard rehabilitation trajectory, and the repulsive force gain is increased exponentially according to the magnitude of the normal deviation distance.

[0041] Extract the equipotential surface coordinate data and the corresponding stiffness coefficient matrix of the virtual elastic potential energy field to generate the spatial coordinate constraint parameters.

[0042] As a further aspect of the present invention, the specific formula for calculating the motion compensation coefficient by the coefficient generation submodule is as follows:

[0043] ;

[0044] in, Represents the aforementioned motion compensation coefficient. The Euclidean norm representing the compensating torque component, The Euclidean norm representing the end-drive torque. This represents the pre-defined cumulative penalty factor for compensation. This represents the real-time position error value of the end effector deviating from the tangent vector of the standard rehabilitation training trajectory. This represents the start time of the training cycle. Represents the current moment.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In this invention, real-time motion data is accurately captured by activating multi-channel sensors and combining joint torque and position feedback. Frequency domain analysis and linear regression are performed on electromyographic signals to construct an electromyographic fatigue gradient. Rigid body dynamics model is used to solve the end-effector driving torque and decompose the proportion of compensatory torque. Based on the compensation coefficient and fatigue state, the resistance increment is dynamically adjusted and a reverse virtual wall spatial constraint is constructed. This enables in-depth perception and quantitative analysis of the patient's physiological characteristics and motion state, ensuring adaptive matching of the best rehabilitation strategy while ensuring training safety, and effectively improving the intelligence and accuracy of rehabilitation training. Attached Figure Description

[0047] Figure 1 This is a block diagram illustrating the principle of the intelligent rehabilitation and nursing management system based on data analysis of the present invention.

[0048] Figure 2 This is a detailed execution flowchart of the motion state acquisition module of the present invention;

[0049] Figure 3 This is a detailed execution flowchart of the physiological characteristic analysis module of the present invention;

[0050] Figure 4 This is a detailed execution flowchart of the motion compensation calculation module of the present invention;

[0051] Figure 5 This is a detailed execution flowchart of the adaptive control execution module of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the software-based technical solution is described in detail below with reference to system architecture diagrams and embodiments. It should be understood that the specific embodiments described herein are only for explaining the technical solutions of this invention and do not constitute a limitation on the scope of protection.

[0053] All user-related information involved in this invention (including but not limited to biometric information, identity verification information, behavioral data, device information, and other data that can be used for identity verification and personalized services) is collected and processed with the user's full knowledge and voluntary consent. The collection, storage, and use of all information strictly comply with applicable national and regional laws and regulations, and meet relevant data protection standards and policy requirements. The use of data is limited to purposes necessary for providing the technical services of this invention, and reasonable technical and management measures will be taken to ensure the security and confidentiality of users' personal information in terms of information protection and privacy.

[0054] In the description of this invention, the system architecture relationships or data processing flows indicated by terms such as "layer," "module," "interface," "data flow," "client," and "server" are all defined based on the architecture diagram or flowchart corresponding to the embodiments. This way of describing is only used to clearly illustrate the logical relationships between the elements in the technical solution, and not to limit the physical deployment form. The term "multiple" includes two or more technical units, including but not limited to multiple data nodes, processing threads, service instances, or functional components and other scalable elements. The specific number is determined according to the actual business scenario and needs to be specifically specified.

[0055] Please see Figure 1 and Figure 2 This invention provides a technical solution: an intelligent rehabilitation and nursing management system based on data analysis, comprising:

[0056] The motion state acquisition module activates multi-channel sensors to acquire raw electromyographic voltage signals of the target muscle group and compensatory muscle group, reads the real-time joint torque value output by the joint torque sensor of the rehabilitation robotic arm, and obtains the real-time angle value fed back by the position encoder.

[0057] The specific functions of the motion state acquisition module are as follows:

[0058] The signal sensing submodule responds to the system start command to activate the multi-channel electromyographic electrode pads attached to the patient's skin surface, and synchronously captures the weak bioelectric signals of the target muscle group and the compensating muscle group at a preset high-frequency sampling rate. It then performs pre-amplification and filtering on the weak bioelectric signals to generate the original electromyographic voltage signal.

[0059] The kinematics reading submodule accesses the joint actuator interface of the rehabilitation robotic arm in real time via the communication bus, reads the torque feedback data of multiple joint torque sensors under high dynamic motion, and simultaneously acquires the absolute angle position data output by the joint position encoder. It performs timestamp alignment and noise reduction processing on the torque feedback data and absolute angle position data to generate real-time joint torque values ​​and real-time angle values.

[0060] The motion state acquisition module is built as the sensing front end of the entire system, responsible for acquiring bioelectrical signals and mechanical data during human-computer interaction with high precision. The specific functions of this module strictly follow a dual parallel architecture of signal sensing and kinematic data acquisition.

[0061] The signal sensing submodule first responds to the start acquisition command issued by the system main control unit. In this embodiment, the command code is set as follows: In response to this command, the signal sensing submodule activates the multichannel electromyographic electrode pads attached to the skin surfaces of the biceps brachii and trapezius muscles of the patient's upper limb via a multiplex analog switch. The biceps brachii is the target muscle group, and the trapezius is the compensatory muscle group. To ensure signal acquisition quality, the electrode pads are selected with a diameter of [missing information]. The Ag / AgCl wet electrode was used, and the skin was cleaned before application to ensure that the skin contact resistance was lower than [value missing]. The signal sensing submodule integrates a precision instrument amplification circuit, configured to... The preset high-frequency sampling rate synchronously captures the weak bioelectrical signals of the aforementioned muscle groups. Considering that the amplitude of the original bioelectrical signals is typically within... to The signal sensing submodule is highly susceptible to environmental noise interference, and first uses a preamplifier to increase the signal gain. The amplification was increased by a factor of 1, and the common-mode rejection ratio was set to be greater than 100%. Subsequently, the amplified analog signal enters the hardware filtering circuit. This circuit is specifically constructed to include a cutoff frequency of... A high-pass filter is used to remove baseline drift, and the cutoff frequency is... A low-pass filter is used to prevent signal aliasing, and a filter with a center frequency of is connected in series. A notch filter is used to eliminate power frequency interference. The signal, after the above analog conditioning, is quantized by an analog-to-digital converter. A sequence of bits is used to generate the original electromyographic voltage signal.

[0062] The aforementioned raw electromyographic voltage signal refers to a voltage time sequence that, after amplification, filtering, and analog-to-digital conversion, can digitally characterize the potential changes generated when muscle fibers are excited.

[0063] To verify the effectiveness of the signal acquisition, an experiment was conducted on a hemiplegic rehabilitation patient. Table 1 shows the signal-to-noise ratio comparison data of the signal sensing submodule at different filtering stages.

[0064] Table 1. Signal-to-noise ratio data at different processing stages of the signal sensing submodule.

[0065] Processing stage peak-to-peak signal noise level Signal-to-noise ratio Signal integrity raw input 1.2mV 0.45mV 8.52dB 65.4% After pre-amplification 1.2V 0.15V 18.06dB 82.1% After filtering 1.15V 0.02V 35.19dB 99.8%

[0066] As shown in Table 1, after step-by-step processing by the signal sensing submodule, the signal-to-noise ratio is significantly improved to [value missing]. This effectively eliminated environmental noise, providing a clean data source for subsequent analysis.

[0067] The kinematics reading submodule is constructed as the underlying sensory neural center of the rehabilitation robotic arm. This submodule establishes a physical connection with the joint actuator interface of the robotic arm via an industrial-grade EtherCAT real-time communication bus, with the communication cycle strictly limited to [time period missing]. To ensure hard real-time data delivery, this submodule is configured to access torque sensors integrated at each joint of the robotic arm in real time. In this embodiment, a strain gauge torque sensor with a range of positive and negative is selected. Accuracy is full scale In high-dynamic motion modes, i.e., angular velocity greater than... At that time, the submodule is The module reads the raw voltage value output by the joint torque sensor at a specific frequency and converts it into a physical quantity, i.e., torque feedback data, according to the sensor calibration curve. Simultaneously, this submodule reads data in parallel from the absolute position encoder mounted on the motor shaft end, which has a resolution of [missing information]. This allows the robot arm to obtain its current absolute angular position data. Given the slight time deviation in sensor data acquisition, this submodule runs a timestamp alignment algorithm. This algorithm reads the distributed clock on the bus and interpolates and maps the sampling times of torque and angle data to the same time reference axis, controlling the maximum alignment error within a certain range. Within. Subsequently, the application length of this submodule is... The moving average filter is used to denoise the data, remove the spike noise caused by mechanical vibration, and finally generate synchronous and smooth real-time joint torque and angle values, which are then packaged and stored in the shared memory area for downstream modules to call.

[0068] The aforementioned EtherCAT refers to an Ethernet control automation technology. It is an open architecture Ethernet fieldbus system with high-speed refresh and low jitter, making it suitable for motion control systems with extremely high real-time requirements.

[0069] Please see Figure 1 and Figure 3 The physiological characteristic analysis module performs a fast Fourier transform on the original electromyographic voltage signal to calculate the power spectral density distribution, extracts the median frequency point sequence in the frequency domain from the power spectral density distribution, calls a linear regression model to calculate the time evolution slope value of the median frequency point sequence in the frequency domain, and constructs the electromyographic fatigue gradient.

[0070] The specific functions of the physiological characteristic analysis module are as follows:

[0071] The spectrum conversion submodule applies windowing truncation to the raw electromyographic voltage signal in the time domain, uses the fast Fourier transform algorithm to map the time domain signal to the frequency domain space, calculates the energy amplitude of multiple frequency components, and generates a power spectral density distribution that characterizes the frequency structure of the electromyographic signal.

[0072] The frequency extraction submodule traverses the power spectral density distribution and calculates the cumulative power spectral energy, identifies the frequency boundary points that divide the cumulative power spectral energy into two equal parts, and continuously extracts the frequency boundary points according to the time sliding window to generate the mid-frequency point sequence in the frequency domain.

[0073] The specific process of calculating the bit frequency point sequence in the frequency domain by the frequency extraction submodule includes:

[0074] Obtain the power spectral density distribution within the current analysis window, and calculate the total power energy value across the entire frequency band from the DC component to the highest effective frequency within the current analysis window;

[0075] The power spectral density distribution is integrated and accumulated starting from zero frequency, and the ratio between the accumulated energy value and the total power energy value of the entire frequency band is monitored in real time.

[0076] When the accumulated energy value first reaches 50% of the total power energy value of the entire frequency band, the corresponding frequency value is locked and marked as the median frequency point of the current analysis window.

[0077] As the time window slides continuously, the above calculation process is repeated and the median frequency points obtained in sequence are arranged in chronological order to generate a frequency domain median frequency point sequence.

[0078] The fatigue assessment submodule uses the mid-frequency point sequence in the frequency domain as the dependent variable and the time series as the independent variable to establish a least squares linear regression equation. It analyzes the slope term of the least squares linear regression equation to quantify the degree of frequency center drift towards lower frequencies and generates an electromyographic fatigue gradient.

[0079] The process of constructing the electromyographic fatigue gradient in the fatigue assessment submodule includes:

[0080] Obtain a frequency point sequence of a preset length in the frequency domain, construct a dataset including time and frequency variables, and fit the trend line of the dataset using a univariate linear regression algorithm.

[0081] Extract the slope parameter of the trend line, determine the sign and magnitude of the slope parameter, and if the slope parameter is negative, define the absolute value of the slope parameter as a quantitative index of muscle fatigue after standardization.

[0082] By combining the physiological tolerance benchmarks of multiple muscle groups, the quantitative indicators of muscle fatigue are normalized and corrected to generate an electromyographic fatigue gradient.

[0083] The core task of the physiological feature analysis module is to convert time-domain electromyographic signals into frequency-domain features and quantify muscle fatigue.

[0084] The spectrum conversion submodule first applies windowing truncation to the input raw electromyographic voltage signal. To reduce spectral leakage, the submodule uses a Hamming window, with the window length set to [value missing]. There are approximately [number] sampling points, corresponding to [number] sampling points. The duration, and the window overlap rate is set to For each windowed time-domain data segment, the submodule calls the Fast Fourier Transform (FFT) logic unit to perform the operation. The specific operation logic utilizes a butterfly arithmetic structure to... Point-domain time-domain sequence conversion A point-wise complex frequency domain sequence. Subsequently, the submodule calculates the energy amplitude of each frequency component, i.e., calculates the square of the modulus of the complex number and divides it by the window normalization coefficient, generating a power spectral density distribution. This distribution is stored as an array, covering values ​​from... to The frequency band, with a frequency resolution of .

[0085] The Hamming window mentioned above is a window function commonly used in signal processing. By smoothing the attenuation of the two ends of the time-domain signal, it can effectively reduce the sidelobe leakage effect in spectrum analysis and improve the spectrum resolution.

[0086] The frequency extraction submodule is configured to calculate the median frequency in the frequency domain based on the power spectral density distribution. This submodule first obtains the power spectral density distribution array within the current analysis window, and then calculates the median frequency from the DC component through accumulation operations. The total power energy value across the entire frequency band up to the highest effective frequency. In this embodiment, the highest effective frequency is set to... Subsequently, the submodule starts from frequency index zero and performs integral accumulation calculations on the power spectral density point by point, monitoring the current accumulated energy value in real time. The submodule internally includes a comparator logic to determine the ratio of the accumulated energy value to the total power energy value across the entire frequency band in real time. The magnitude relationship. When the ratio is first detected to reach or exceed... At that time, the submodule immediately locks the current frequency index and marks the corresponding physical frequency value as the median frequency point of the current analysis window. As the time window progresses... Each slide completes the above calculation process, and the successively obtained median frequency points are stored in a first-in-first-out queue in chronological order to generate a frequency domain median frequency point sequence.

[0087] The fatigue assessment submodule is configured to quantify the degree of muscle fatigue. This submodule reads a frequency domain median frequency sequence of a preset length. In this embodiment, the preset length is set to the most recent... Data in seconds, that is, approximately containing This submodule constructs a dataset containing a matrix of independent variables (time variables) and a matrix of dependent variables (frequency variables). Subsequently, the submodule calls the least squares linear regression algorithm unit. This algorithm unit performs matrix operations to calculate the regression coefficient vector. The submodule extracts the slope term from the regression equation. Physiologically, muscle fatigue is characterized by a shift in median frequency to lower frequencies, meaning the slope should be negative. The submodule determines the sign and magnitude of the slope term; if the slope term is negative, it indicates a fatigue trend. The submodule standardizes the absolute value of the slope parameter, i.e., it calculates the ratio of the absolute value of the slope to a preset reference slope for severe fatigue. In this embodiment, the reference slope for severe fatigue is set to... Finally, the submodule combines the physiological tolerance benchmarks for this specific muscle group stored in the database to normalize and correct the indicators, generating the final electromyographic fatigue gradient. In this embodiment, the physiological tolerance benchmark for the biceps brachii is set as follows: Trapezius muscle set as .

[0088] Table 2 shows the module's performance in a continuous... Measured data and calculation results from isometric contraction training over seconds.

[0089] Table 2 Data table of electromyographic fatigue gradient calculation process

[0090] Time period MDF sequence mean Calculate the slope Judgment Result Fatigue index electromyographic fatigue gradient 0−10s 95.4Hz −0.05 No obvious fatigue 0.06 0.06 10−20s 88.2Hz −0.42 Mild fatigue 0.52 0.52 20−30s 76.5Hz −0.85 Severe fatigue 1.06 1.06

[0091] As shown in Table 2, the absolute value of the median frequency slope increased significantly as training progressed. The electromyographic fatigue gradient calculated by the system accurately reflected the changes in muscle state. This result indicates that the system can quantify and capture subtle physiological fatigue trends.

[0092] Please see Figure 1 and Figure 4 The motion compensation calculation module inputs real-time joint torque and angle values ​​into the rigid body dynamics model to solve the end-drive torque, decomposes the end-drive torque into target torque components and compensation torque components, calculates the proportion of the compensation torque component in the end-drive torque, and generates motion compensation coefficients.

[0093] The specific functions of the motion compensation calculation module are as follows:

[0094] The dynamics solution submodule obtains the link mass parameters and inertia tensor matrix of the robotic arm, combines them with real-time joint torque and angle values, and uses the Lagrange dynamics equations to solve the force state of the robotic arm end effector in the Cartesian coordinate system, generating the end-effector driving torque.

[0095] The process by which the dynamics solution submodule generates the end-drive torque includes:

[0096] Call the robot arm link length, link center of mass position and link mass parameters stored in the system database;

[0097] Based on real-time angle numerical calculations of the angular velocities and angular accelerations of multiple joints, and using the inverse kinematics algorithm for rigid body dynamics, the theoretical joint torques required to counteract the gravity, Coriolis force, and centrifugal force terms are calculated.

[0098] Calculate the difference vector between the real-time joint torque value and the theoretical joint torque, and use the Jacobian matrix transpose method to map the difference vector to the end effector space to generate the end effector driving torque;

[0099] The torque decomposition submodule obtains the preset standard rehabilitation training trajectory tangent vector, orthogonally projects the end-drive torque onto the direction of the standard rehabilitation training trajectory tangent vector to separate the target torque component, and defines the remaining vector after removing the target torque component from the end-drive torque as the compensating torque component.

[0100] The coefficient generation submodule calculates the ratio between the modulus of the compensating torque component and the modulus of the end-drive torque, and performs weighted correction by combining the current motion smoothness index comparison value to generate motion compensation coefficients.

[0101] The specific formula for calculating the motion compensation coefficient by the coefficient generation submodule is as follows:

[0102] ;

[0103] in, Represents the coefficient of motion compensation. The Euclidean norm representing the compensating torque component, The Euclidean norm represents the end-drive torque. This represents the pre-defined cumulative penalty factor for compensation. This represents the real-time position error value of the end effector deviating from the tangent vector of the standard rehabilitation training trajectory. This represents the start time of the training cycle. Represents the current moment.

[0104] The motion compensation calculation module uses dynamics calculation and torque decomposition techniques to accurately quantify the compensatory behavior of patients during training.

[0105] The dynamics calculation submodule is configured to infer the end effector force based on the robot's motion state. This submodule first retrieves pre-stored robotic arm link parameters from the system database, including link lengths. for , for and connecting rod mass parameters for , for Combining real-time acquired joint angles with angular velocities and angular accelerations calculated through differential methods, this submodule performs inverse kinematics calculations using the Lagrange equations. This process calculates the theoretical joint torque required to counteract the robot arm's own gravity and inertial forces. Subsequently, the submodule calculates the difference vector between the real-time joint torque value and the theoretical joint torque. This difference vector represents the pure interactive torque exerted on the robot arm by the external force, i.e., the patient's limb. Finally, the submodule uses the Jacobian matrix transpose method to map this joint space torque to Cartesian space, generating the end effector driving torque.

[0106] The Jacobian matrix transpose method mentioned above refers to a method that uses the transpose of the robot's Jacobian matrix to linearly map the torque vector in the joint space to the operating force or torque vector in the end-effector Cartesian space.

[0107] The torque decomposition submodule and the coefficient generation submodule work together to quantify the degree of compensation. The torque decomposition submodule obtains the tangent vector of the preset standard rehabilitation training trajectory at the current moment. This submodule performs vector projection operation, projecting the end-effector driving torque onto the direction of the tangent vector of the standard rehabilitation training trajectory, and calculates the target torque component. Simultaneously, it calculates the compensating torque component through vector subtraction. This step decomposes the force applied by the patient into effective work force and ineffective compensatory force perpendicular to the direction of movement.

[0108] The coefficient generation submodule calculates the motion compensation coefficients according to the following formula:

[0109] ;

[0110] in, The coefficient representing the motion compensation is used to comprehensively evaluate the current degree of compensation. The Euclidean norm represents the compensating torque component, i.e., the magnitude of the ineffective torque; The Euclidean norm represents the end-drive torque, which is the magnitude of the total drive torque applied by the patient; This represents a preset compensation cumulative penalty factor, used to adjust the weight of the influence of historical position errors on the current compensation coefficient. In this embodiment, it is set to a value of [value missing]. ; This represents the integral term of the position error, which is the accumulation of the real-time position error value of the end effector deviating from the tangent vector of the standard rehabilitation training trajectory over time. Represents the start time of the training cycle; Represents the current moment.

[0111] In this embodiment, the parameters in the formula are specifically configured and calculated as follows to verify its technical effect. Assume that at a certain moment, the end-drive torque vector is calculated in real-time by the dynamics solution submodule as follows: Its Euclidean norm is Assuming the standard trajectory tangent vector is along the positive X-axis, the compensated component is calculated as follows: Its norm is Assume that the training has continued from the start to the current time. The system is based on Frequency sampling, the average distance of the end effector deviating from the standard trajectory is The approximate value of the integral is Substitute the above values ​​into the formula for calculation: First, calculate the torque ratio. Then calculate the penalty term as follows: The final calculated compensation coefficient is: .

[0112] Table 3. Calculation Examples of Motion Compensation Coefficient

[0113]

[0114] This result indicates that, although instantaneous torque compensation accounts for only a small percentage... However, due to the patient's persistent cumulative positional deviation, the final compensation coefficient is amplified by the penalty term. The advantage of this formula is that it not only considers the current error in the direction of force, but also introduces historical evaluation over time through the integral term. This effectively identifies implicit compensatory behaviors where the body posture is skewed for a long time, even if the direction of force is barely correct, making the compensation assessment more comprehensive and rigorous.

[0115] Please see Figure 1 and Figure 5 The adaptive control execution module calculates the resistance increment value based on the electromyographic fatigue gradient and generates motor current control commands. When the motion compensation coefficient exceeds the preset threshold, it calculates the spatial coordinate constraint parameters of the reverse virtual wall and constructs a rehabilitation control strategy based on the motor current control commands and spatial coordinate constraint parameters.

[0116] The specific functions of the adaptive control execution module are as follows:

[0117] The resistance adjustment submodule establishes a nonlinear mapping relationship between the electromyographic fatigue gradient and the motor output impedance. As the electromyographic fatigue gradient increases, the training resistance setting value is dynamically reduced. Based on the adjusted training resistance setting value, the target current value of multiple joint motors is calculated, and motor current control commands are generated.

[0118] The constraint construction submodule monitors the motion compensation coefficient in real time. When the motion compensation coefficient exceeds the preset compensation range, it generates a virtual force field boundary with stiffness and damping characteristics outside the standard trajectory based on the current deviation direction, calculates the geometric position data of the virtual force field boundary, and generates spatial coordinate constraint parameters.

[0119] The process of generating spatial coordinate constraint parameters by the constraint construction submodule includes:

[0120] Obtain the three-dimensional spatial point set of the standard rehabilitation trajectory, and when the motion compensation coefficient exceeds the preset threshold, calculate the normal deviation distance between the current actual position of the end effector and the standard rehabilitation trajectory.

[0121] A virtual elastic potential energy field is constructed based on the normal deviation distance. The direction of the repulsive force of the virtual elastic potential energy field is set to be perpendicular to the inside of the standard rehabilitation trajectory, and the repulsive force gain is increased exponentially according to the magnitude of the normal deviation distance.

[0122] Extract the equipotential surface coordinate data and the corresponding stiffness coefficient matrix of the virtual elastic potential energy field to generate spatial coordinate constraint parameters;

[0123] The strategy fusion submodule uses motor current control commands as the underlying torque following basis and spatial coordinate constraint parameters as position constraints. Through an impedance controller, torque control and position constraints are logically superimposed to generate a rehabilitation control strategy.

[0124] The adaptive control execution module dynamically adjusts the control strategy of the robotic arm based on the front-end analysis results to achieve intelligent assistance.

[0125] The resistance adjustment submodule is configured to dynamically adjust the physical parameters of rehabilitation training based on the aforementioned generated electromyographic fatigue gradient. The submodule internally uses a preset nonlinear mapping function, where the damping coefficient equals the initial damping setpoint multiplied by a negative power of the natural constant, where the power is the product of the decay rate constant and the electromyographic fatigue gradient. In this embodiment, the initial damping setpoint is set to... The decay rate constant is set to If the current electromyographic fatigue gradient is calculated as follows: Then the system calculates the new damping coefficient. The calculation process is as follows: the exponential part is... Multiply equal natural constant The power is approximately The final new damping coefficient is Multiply equal Subsequently, the submodule calculates the target current value that each joint motor needs to output based on the adjusted resistance setting and the current movement speed, and generates motor current control commands, thereby automatically reducing the current when the patient is fatigued. The training resistance helps prevent muscle damage.

[0126] The constraint construction submodule is configured to intervene when severe compensation is detected. This submodule monitors the motion compensation coefficient in real time. The system sets a preset threshold. In the above example, the calculated compensation coefficient is: The threshold has been exceeded. At this point, the constraint construction submodule immediately triggers the virtual wall generation logic. This submodule acquires the three-dimensional spatial point set of the standard rehabilitation trajectory and calculates the normal deviation distance from the current position of the end effector to the nearest point on the trajectory. A virtual elastic potential energy field is constructed based on the normal deviation distance. This submodule sets the virtual stiffness not to be constant, but to increase exponentially with distance. In this embodiment, the basic stiffness is set to be... The gain coefficient is If the current deviation distance is The stiffness provided by the virtual wall is calculated as follows: Multiplied by the natural constant The result of subtracting one from the power is:

[0127] This submodule calculates the corresponding repulsive force vector and defines the repulsive force and the corresponding stiffness matrix as spatial coordinate constraint parameters.

[0128] The strategy fusion submodule ultimately fuses the above parameters through an impedance controller. It receives motor current control commands as feedforward torque and spatial coordinate constraint parameters as feedback correction force, generating the final force through logical superposition. The rehabilitation control strategy signals drive the robotic arm to provide appropriate training resistance and form a flexible tunnel in space, forcibly constraining the patient's movements within a safe range.

[0129] The above embodiments illustrate preferred embodiments of the present invention. Any equivalent adjustments to the technical solution based on software engineering methods are within the scope of protection, including but not limited to: implementing algorithm logic using different programming languages, refactoring functional modules into services, adjusting data interaction protocols, and optimizing resource scheduling strategies. Any implementation scheme derived from reasonable modifications to the data processing flow, service call chain, or system architecture layer without departing from the core technology of the present invention should be considered within the protection scope defined by the technical solution of the present invention.

Claims

1. An intelligent rehabilitation and nursing management system based on data analysis, characterized in that, The system includes: The motion state acquisition module activates multi-channel sensors to acquire raw electromyographic voltage signals of the target muscle group and compensatory muscle group, reads the real-time joint torque value output by the joint torque sensor of the rehabilitation robotic arm, and obtains the real-time angle value fed back by the position encoder. The physiological characteristic analysis module has the following specific functions: The spectrum conversion submodule applies windowing truncation processing to the original electromyographic voltage signal in the time domain, uses the fast Fourier transform algorithm to map the time domain signal to the frequency domain space, calculates the energy amplitude of multiple frequency components, and generates a power spectral density distribution that characterizes the frequency structure of the electromyographic signal. The frequency extraction submodule traverses the power spectral density distribution and calculates the cumulative power spectral energy, identifies the frequency boundary points that divide the cumulative power spectral energy into two equal parts, and continuously extracts the frequency boundary points according to the time sliding window to generate the frequency domain median frequency point sequence. The fatigue assessment submodule uses the mid-frequency point sequence in the frequency domain as the dependent variable and the time series as the independent variable to establish a least squares linear regression equation. It analyzes the slope term of the least squares linear regression equation to quantify the degree of frequency center drift towards lower frequencies and generates the electromyographic fatigue gradient. The motion compensation calculation module has the following specific functions: The dynamics solution submodule obtains the link mass parameters and inertia tensor matrix of the robotic arm, and combines the real-time joint torque value and the real-time angle value to use the Lagrange dynamics equation to solve the force state of the robotic arm end effector in the Cartesian coordinate system, thereby generating the end-effector driving torque. The torque decomposition submodule obtains the preset standard rehabilitation training trajectory tangent vector, orthogonally projects the end driving torque onto the direction of the standard rehabilitation training trajectory tangent vector to separate the target torque component, and defines the remaining vector after removing the target torque component from the end driving torque as the compensating torque component. The coefficient generation submodule calculates the ratio between the modulus of the compensating torque component and the modulus of the end drive torque, and performs a weighted correction on the ratio in conjunction with the current motion smoothness index to generate the motion compensation coefficient. The adaptive control execution module calculates the resistance increment value based on the electromyographic fatigue gradient and generates a motor current control command. When the motion compensation coefficient exceeds a preset threshold, it calculates the spatial coordinate constraint parameters of the reverse virtual wall and constructs a rehabilitation control strategy based on the motor current control command and the spatial coordinate constraint parameters.

2. The intelligent rehabilitation and nursing management system based on data analysis according to claim 1, characterized in that, The specific functions of the motion state acquisition module are as follows: The signal sensing submodule responds to the system start command to activate the multi-channel electromyographic electrode pads attached to the patient's skin surface, and synchronously captures the weak bioelectric signals of the target muscle group and the compensating muscle group at a preset high-frequency sampling rate. The weak bioelectric signals are pre-amplified and filtered to generate the original electromyographic voltage signal. The kinematic reading submodule accesses the joint actuator interface of the rehabilitation robotic arm in real time via the communication bus, reads torque feedback data from multiple joint torque sensors under high dynamic motion, and simultaneously acquires absolute angle position data output by the joint position encoder. The torque feedback data and the absolute angle position data are then time-stamped and denoised to generate the real-time joint torque value and the real-time angle value.

3. The intelligent rehabilitation and nursing management system based on data analysis according to claim 1, characterized in that, The specific functions of the adaptive control execution module are as follows: The resistance adjustment submodule establishes a nonlinear mapping relationship between the electromyographic fatigue gradient and the motor output impedance. As the electromyographic fatigue gradient increases, the training resistance setting value is dynamically reduced. Based on the adjusted training resistance setting value, the target current values ​​of multiple joint motors are calculated, and the motor current control command is generated. The constraint construction submodule monitors the motion compensation coefficient in real time. When the motion compensation coefficient exceeds the preset compensation range, it generates a virtual force field boundary with stiffness and damping characteristics outside the standard trajectory based on the current deviation direction, calculates the geometric position data of the virtual force field boundary, and generates the spatial coordinate constraint parameters. The strategy fusion submodule uses the motor current control command as the underlying torque following basis and the spatial coordinate constraint parameters as position restriction conditions. The torque control and position restriction are logically superimposed through the impedance controller to generate the rehabilitation control strategy.

4. The intelligent rehabilitation and nursing management system based on data analysis according to claim 1, characterized in that, The specific process by which the frequency extraction submodule calculates the mid-frequency point sequence in the frequency domain includes: Obtain the power spectral density distribution within the current analysis window, and calculate the total power energy value across the entire frequency band from the DC component to the highest effective frequency within the current analysis window; The power spectral density distribution is integrated and accumulated starting from zero frequency, and the ratio between the accumulated energy value and the total power energy value of the entire frequency band is monitored in real time. When the accumulated energy value first reaches 50% of the total power energy value of the entire frequency band, the corresponding frequency value is locked and the frequency value is marked as the median frequency point of the current analysis window. As the time window slides continuously, the above calculation process is repeated, and the median frequency points obtained in sequence are arranged in chronological order to generate the frequency domain median frequency point sequence.

5. The intelligent rehabilitation and nursing management system based on data analysis according to claim 1, characterized in that, The process of constructing the electromyographic fatigue gradient by the fatigue assessment submodule includes: Obtain the frequency point sequence of the frequency domain of the preset length, construct a dataset including time variables and frequency variables, and fit the trend line of the dataset using a univariate linear regression algorithm; Extract the slope parameter of the trend line, determine the sign and magnitude of the slope parameter, and if the slope parameter is negative, define the absolute value of the slope parameter as a quantitative index of muscle fatigue after standardization. The muscle fatigue quantification index is normalized and corrected by combining the physiological tolerance benchmarks of multiple muscle groups to generate the electromyographic fatigue gradient.

6. The intelligent rehabilitation and nursing management system based on data analysis according to claim 1, characterized in that, The process by which the dynamics calculation submodule generates the end-drive torque includes: Call the robot arm link length, link center of mass position, and link mass parameters stored in the system database; Based on the real-time angle values, the angular velocities and angular accelerations of multiple joints are calculated. Then, according to the inverse kinematics algorithm, the theoretical joint torques required to counteract the gravity, Coriolis force, and centrifugal force terms are calculated. The difference vector between the real-time joint torque value and the theoretical joint torque is calculated, and the difference vector is mapped to the end effector space using the Jacobian matrix transpose method to generate the end effector driving torque.

7. The intelligent rehabilitation and nursing management system based on data analysis according to claim 3, characterized in that, The process by which the constraint construction submodule generates the spatial coordinate constraint parameters includes: Obtain a three-dimensional spatial point set of the standard rehabilitation trajectory; when the motion compensation coefficient exceeds a preset threshold, calculate the normal deviation distance between the current actual position of the end effector and the standard rehabilitation trajectory. A virtual elastic potential energy field is constructed based on the normal deviation distance. The repulsive force direction of the virtual elastic potential energy field is set to be perpendicular to the inside of the standard rehabilitation trajectory, and the repulsive force gain is increased exponentially according to the magnitude of the normal deviation distance. Extract the equipotential surface coordinate data and the corresponding stiffness coefficient matrix of the virtual elastic potential energy field to generate the spatial coordinate constraint parameters.

8. The intelligent rehabilitation and nursing management system based on data analysis according to claim 1, characterized in that, The specific formula for calculating the motion compensation coefficient by the coefficient generation submodule is as follows: ； in, Represents the aforementioned motion compensation coefficient. The Euclidean norm representing the compensating torque component, The Euclidean norm representing the end-drive torque. This represents the pre-defined cumulative penalty factor for compensation. This represents the real-time position error value of the end effector deviating from the tangent vector of the standard rehabilitation training trajectory. This represents the start time of the training cycle. It represents the current moment.

Images